arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.01502cs.CLcs.AI
收藏

基于心理理论的计算语言习得

Computational Language Acquisition with Theory of Mind

Harvey Mudd College(哈维穆德学院);Carnegie Mellon University(卡内基梅隆大学)

Andy Liu, Hao Zhu, Emmy Liu, Yonatan Bisk, Graham Neubig

摘要:

与目前最先进的语言模型不同,幼儿通过与周围环境和照顾者的互动来主动习得语言。一种被认为对语言学习至关重要的机制是推断社会环境中其他主体的心理状态的能力,由Premack和Woodruff(1978)创造的心理理论(ToM)。从Rabinowitz et al.(2018)和Zhu et al.(2021)实现的ToM的现代操作化版本中汲取灵感,我们构建了配备ToM的语言学习代理,并测量其对学习过程的影响。我们给说话者代理一个内部的听者模型,该模型与说话者一起训练,并用于对潜在的话语进行重新排序。我们用不同的任务难度进行实验,假设模型将获得更复杂的语言来适应更强的环境压力。我们发现,训练扬声器与一个高度加权的ToM听众组件导致性能增益在我们的图像参考游戏设置。我们还发现一些证据表明,在训练过程中增加任务难度会导致更流畅和准确的话语评价。这表明进一步将心理理论以及儿童语言习得的其他见解纳入语言习得的计算模型的潜在效用。

英文摘要:

Unlike current state-of-the-art language models, young children actively acquire language through interactions with their surrounding environment and caretakers. One mechanism that has been argued to be critical to language learning is the ability to infer the mental states of other agents in social environments, coined Theory of Mind (ToM) by Premack & Woodruff (1978). Drawing inspiration from the modern operationalized versions of ToM implemented in Rabinowitz et al. (2018) and Zhu et al. (2021), we build language-learning agents equipped with ToM, and measure its effects on the learning process. We model ToM by giving the speaker agent an internal listener model that is trained alongside the speaker and used to rerank potential utterances. We experiment with varying task difficulty, hypothesizing that models will acquire more complex language to adapt to stronger environmental pressures. We find that training speakers with a highly weighted ToM listener component leads to performance gains in our image referential game setting. We also find some evidence that increasing task difficulty in the training process results in more fluent and precise utterances in evaluation. This suggests the potential utility of further incorporating ToM, as well as other insights from child language acquisition, into computational models of language acquisition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑